By organizing data in this manner, it can be easily visually understood. One can see that higher deaths and cases seem to correlate with lower incomes, and vice versa. As one looks from left to right on this graph, incidence decreases. This is affirmed by the trendline, as they both are negative and linear. Further, the R2 values show how strong the model is. As it is 0.934 for cases (very strong) and 0.771 for deaths (strong), this figure shows that there is a correlation between median income and the effect of COVID-19 on a population.

The scatterplot shown above demonstrates all of my raw data of 2018 placed into a visual representation that can help identify the type of correlation that the two variables have. Regarding the asterisk, that is representative of the y value  on each data point representing the number of people who died from firearms in one state from every thousand people. In the data, There is heavy clumping of data along a low x value and middle to high y value which means that there are the most deaths occurring in a state when there is less funding from gun rights groups. That being said, many of the states that had no funding have the lowest death rates of all of the data. There is a specific positive strong correlation between $100,000 and $200,000 on the x axis and 7 to 21 deaths on the x axis. This strong, positive correlation can only be seen in this part of the graph so it is not representative of all of the data. Therefore, this data is not representative of my initial hypothesis. There is a very clear outlier in the data along the right side of the scatter plot however there are other possible outliers that I will calculate for.

 The second graph here is my data presented geographically, also known as geospatial data. I choose to represent my data this way because according to Everytown Research and Policy, the nonprofit source my data came from, “Even the strongest system can’t protect a state from its neighbors’ weak laws. The rankings clearly show that gun laws save lives. But no state is an island (except Hawaii), and any state may be vulnerable if its neighbors fail to protect public safety.” After reading this fact, I wanted to look at how gun law violence spreads out across the country, in order to recognize how gun control in one state may affect gun safety in another. Consequently, this diagram illustrates that the stages of the gun law process are spread out all across the country. States like Illinois, which is a national leader, are bordered by states like Missouri, which is a national failure. According to the research, while state laws may give states the power over gun control within their borders, as a country only federal law can ensure the protection of states entirely, because due to our country's geographical layout, as long as some states can choose to have weak gun violence, all other states are in danger. 

S =  d/t 

S being speed,

d being distance,

and t being time.

By collecting information about the average wingspan of each sample group, I can estimate at what distance the pitcher will release the ball from the plate (for example, a 6’2 pitcher releasing the ball at 56 feet from the plate).

(For context, the pitching mound is 60.5 feet away from home plate, but the stride that a pitcher takes decreases this distance). 

By calculating the time it takes a 100 mph fastball to reach home plate from the largest wingspan (using s=d/t), I can implement the time of that pitch to the distances appropriate for the other 2 distances. Thus, finding the “perceived” speed of the ball when thrown closer to the plate.

The use of a map enables me to have a broad global outlook on how my two variables relate to each other. I found this one particularly useful because it organizes the data by color, giving clear indication of the happiness value. This means that patterns and trends in the data, especially across certain regions, can be more identifiable. Additionally, I can also measure the influences of other geographical factors in the data, such as the size of a country, and its proximity to other countries.

The data produced a R value of 0.028. This indicates that there is a weak, positive, linear link between a celebrity's Instagram followers and their brand's annual revenue. The scatter plot above illustrates that an increase in followers leads to a slight rise in brand income. Due to the very low r-value and slope of the line of best fit, this is not a compelling claim. There is minimal evidence of a link between influencers with less than 50 million followers and their brand's annual revenue, as the dots are dispersed and do not follow any pattern or trend. This is clear in the second image of the graph's zoomed-in region. This scatter plot also displays some data outliers. These are data points that do not follow the trend in any way. One exception is Jessica Simpson's brand, Jessica Simpson Shoes, which has a revenue of over $1 billion but a following of roughly 7 million. This point is far off from the line of best fit and goes against the general trend of the data in the chart. This is an extreme example that shows virtually little link between a large following and a large profit. This outlier also has a significant impact on the R-value to decrease the correlation coefficient.  

The scatter plot shows that despite not being extremely strong, there is a correlation between these two variables. As the years of education after high school increase, there is a general increase in the SAT score. This is clear in the line of best fit which is included in the graph. The line of best fit has an upward slope. There are clear points which deviate from this correlation. The 960 is an outlier as it has a large distance from the line of best fit. As you get further from the line of best fit there will be more outliers visible.

On this bar graph, the control group, which is the group that does not have congenital heart disease, and the case group, which is the group that has congenital heart disease are measured in the same way but need to be distinguished because they are different. This graph measures the frequency of different numbers of attributes. According to the graph, the control group’s frequency of attributes decreases as the number of attributes increases. In the case group, this trend is similar but the frequency of having zero attributes in the case group is lower than the frequency of having one attribute in the case group. It can also be drawn from this graph that the case group has a higher frequency of one or more attributes while the control group has a lower frequency of having one or more attributes.